jikechao opened a new issue, #14614: URL: https://github.com/apache/tvm/issues/14614
For the following ONNX model, ONNXConverter will mistakenly parse the output number and thus triggered an assertion failure. ### The ONNX structure:  You can download the model by this link: https://github.com/jikechao/onnx_models/blob/main/model.onnx ### Crash message: ``` Traceback (most recent call last): ... irmod, params = relay.frontend.from_onnx(predict_model, shape_dict, freeze_params=True) File "/workplace/software/tvm/tvm/python/tvm/relay/frontend/onnx.py", line 7346, in from_onnx mod, params = g.from_onnx(graph, opset) File "/workplace/software/tvm/tvm/python/tvm/relay/frontend/onnx.py", line 6963, in from_onnx self._construct_nodes(graph) File "/workplace/software/tvm/tvm/python/tvm/relay/frontend/onnx.py", line 7120, in _construct_nodes len(node_output), outputs_num, op_name AssertionError: Number of output mismatch 2 vs 1 in MaxPool. ``` ### reproducible script: ``` import onnx from tvm import relay onnx_model_path = "model.onnx" model = onnx.load(onnx_model_path) irmod, params = relay.frontend.from_onnx(model, {'x': (1, 1, 5, 5)}, freeze_params=True) ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
